#import ipmoratant libraries
#libraries to  read and manipulate data
import pandas as pd
import numpy as np
#libraries used in visualization
import plotly.express as px
!pip install ipywidgets
!jupyter nbextension enable --py widgetsnbextension
from ipywidgets import interact, interactive, fixed, interact_manual
import ipywidgets as widgets

Requirement already satisfied: ipywidgets in e:\anaconda3\lib\site-packages (7.6.3)
Requirement already satisfied: ipykernel>=4.5.1 in e:\anaconda3\lib\site-packages (from ipywidgets) (5.3.4)
Requirement already satisfied: traitlets>=4.3.1 in e:\anaconda3\lib\site-packages (from ipywidgets) (5.0.5)
Requirement already satisfied: jupyterlab-widgets>=1.0.0 in e:\anaconda3\lib\site-packages (from ipywidgets) (1.0.0)
Requirement already satisfied: nbformat>=4.2.0 in e:\anaconda3\lib\site-packages (from ipywidgets) (5.1.3)
Requirement already satisfied: widgetsnbextension~=3.5.0 in e:\anaconda3\lib\site-packages (from ipywidgets) (3.5.1)
Requirement already satisfied: ipython>=4.0.0 in e:\anaconda3\lib\site-packages (from ipywidgets) (7.22.0)
Requirement already satisfied: jupyter-client in e:\anaconda3\lib\site-packages (from ipykernel>=4.5.1->ipywidgets) (6.1.12)
Requirement already satisfied: tornado>=4.2 in e:\anaconda3\lib\site-packages (from ipykernel>=4.5.1->ipywidgets) (6.1)
Requirement already satisfied: pygments in e:\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (2.8.1)
Requirement already satisfied: setuptools>=18.5 in e:\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (52.0.0.post20210125)
Requirement already satisfied: colorama in e:\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (0.4.4)
Requirement already satisfied: pickleshare in e:\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (0.7.5)
Requirement already satisfied: jedi>=0.16 in e:\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (0.17.2)
Requirement already satisfied: decorator in e:\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (5.0.6)
Requirement already satisfied: backcall in e:\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (0.2.0)
Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in e:\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (3.0.17)
Requirement already satisfied: parso<0.8.0,>=0.7.0 in e:\anaconda3\lib\site-packages (from jedi>=0.16->ipython>=4.0.0->ipywidgets) (0.7.0)
Requirement already satisfied: jupyter-core in e:\anaconda3\lib\site-packages (from nbformat>=4.2.0->ipywidgets) (4.7.1)
Requirement already satisfied: jsonschema!=2.5.0,>=2.4 in e:\anaconda3\lib\site-packages (from nbformat>=4.2.0->ipywidgets) (3.2.0)
Requirement already satisfied: ipython-genutils in e:\anaconda3\lib\site-packages (from nbformat>=4.2.0->ipywidgets) (0.2.0)
Requirement already satisfied: attrs>=17.4.0 in e:\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.2.0->ipywidgets) (20.3.0)
Requirement already satisfied: six>=1.11.0 in e:\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.2.0->ipywidgets) (1.15.0)
Requirement already satisfied: pyrsistent>=0.14.0 in e:\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.2.0->ipywidgets) (0.17.3)
Requirement already satisfied: wcwidth in e:\anaconda3\lib\site-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython>=4.0.0->ipywidgets) (0.2.5)
Requirement already satisfied: notebook>=4.4.1 in e:\anaconda3\lib\site-packages (from widgetsnbextension~=3.5.0->ipywidgets) (6.3.0)
Requirement already satisfied: jinja2 in e:\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (2.11.3)
Requirement already satisfied: argon2-cffi in e:\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (20.1.0)
Requirement already satisfied: nbconvert in e:\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (6.0.7)
Requirement already satisfied: terminado>=0.8.3 in e:\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.9.4)
Requirement already satisfied: pyzmq>=17 in e:\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (20.0.0)
Requirement already satisfied: prometheus-client in e:\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.10.1)
Requirement already satisfied: Send2Trash>=1.5.0 in e:\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.5.0)
Requirement already satisfied: python-dateutil>=2.1 in e:\anaconda3\lib\site-packages (from jupyter-client->ipykernel>=4.5.1->ipywidgets) (2.8.1)
Requirement already satisfied: pywin32>=1.0 in e:\anaconda3\lib\site-packages (from jupyter-core->nbformat>=4.2.0->ipywidgets) (227)
Requirement already satisfied: pywinpty>=0.5 in e:\anaconda3\lib\site-packages (from terminado>=0.8.3->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.5.7)
Requirement already satisfied: cffi>=1.0.0 in e:\anaconda3\lib\site-packages (from argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.14.5)
Requirement already satisfied: pycparser in e:\anaconda3\lib\site-packages (from cffi>=1.0.0->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (2.20)
Requirement already satisfied: MarkupSafe>=0.23 in e:\anaconda3\lib\site-packages (from jinja2->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.1.1)
Requirement already satisfied: bleach in e:\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (3.3.0)
Requirement already satisfied: testpath in e:\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.4.4)
Requirement already satisfied: entrypoints>=0.2.2 in e:\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.3)
Requirement already satisfied: jupyterlab-pygments in e:\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.1.2)
Requirement already satisfied: pandocfilters>=1.4.1 in e:\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.4.3)
Requirement already satisfied: defusedxml in e:\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.7.1)
Requirement already satisfied: mistune<2,>=0.8.1 in e:\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.8.4)
Requirement already satisfied: nbclient<0.6.0,>=0.5.0 in e:\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.5.3)
Requirement already satisfied: nest-asyncio in e:\anaconda3\lib\site-packages (from nbclient<0.6.0,>=0.5.0->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.5.1)
Requirement already satisfied: async-generator in e:\anaconda3\lib\site-packages (from nbclient<0.6.0,>=0.5.0->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.10)
Requirement already satisfied: packaging in e:\anaconda3\lib\site-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (20.9)
Requirement already satisfied: webencodings in e:\anaconda3\lib\site-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.5.1)
Requirement already satisfied: pyparsing>=2.0.2 in e:\anaconda3\lib\site-packages (from packaging->bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (2.4.7)

Enabling notebook extension jupyter-js-widgets/extension...
      - Validating: ok

#read data
df = pd.read_csv('tmdb-movies.csv')
df

	id	imdb_id	popularity	budget	revenue	original_title	cast	homepage	director	tagline	...	overview	runtime	genres	production_companies	release_date	vote_count	vote_average	release_year	budget_adj	revenue_adj
0	135397	tt0369610	32.985763	150000000	1513528810	Jurassic World	Chris Pratt|Bryce Dallas Howard|Irrfan Khan|Vi...	http://www.jurassicworld.com/	Colin Trevorrow	The park is open.	...	Twenty-two years after the events of Jurassic ...	124	Action|Adventure|Science Fiction|Thriller	Universal Studios|Amblin Entertainment|Legenda...	6/9/15	5562	6.5	2015	1.379999e+08	1.392446e+09
1	76341	tt1392190	28.419936	150000000	378436354	Mad Max: Fury Road	Tom Hardy|Charlize Theron|Hugh Keays-Byrne|Nic...	http://www.madmaxmovie.com/	George Miller	What a Lovely Day.	...	An apocalyptic story set in the furthest reach...	120	Action|Adventure|Science Fiction|Thriller	Village Roadshow Pictures|Kennedy Miller Produ...	5/13/15	6185	7.1	2015	1.379999e+08	3.481613e+08
2	262500	tt2908446	13.112507	110000000	295238201	Insurgent	Shailene Woodley|Theo James|Kate Winslet|Ansel...	http://www.thedivergentseries.movie/#insurgent	Robert Schwentke	One Choice Can Destroy You	...	Beatrice Prior must confront her inner demons ...	119	Adventure|Science Fiction|Thriller	Summit Entertainment|Mandeville Films|Red Wago...	3/18/15	2480	6.3	2015	1.012000e+08	2.716190e+08
3	140607	tt2488496	11.173104	200000000	2068178225	Star Wars: The Force Awakens	Harrison Ford|Mark Hamill|Carrie Fisher|Adam D...	http://www.starwars.com/films/star-wars-episod...	J.J. Abrams	Every generation has a story.	...	Thirty years after defeating the Galactic Empi...	136	Action|Adventure|Science Fiction|Fantasy	Lucasfilm|Truenorth Productions|Bad Robot	12/15/15	5292	7.5	2015	1.839999e+08	1.902723e+09
4	168259	tt2820852	9.335014	190000000	1506249360	Furious 7	Vin Diesel|Paul Walker|Jason Statham|Michelle ...	http://www.furious7.com/	James Wan	Vengeance Hits Home	...	Deckard Shaw seeks revenge against Dominic Tor...	137	Action|Crime|Thriller	Universal Pictures|Original Film|Media Rights ...	4/1/15	2947	7.3	2015	1.747999e+08	1.385749e+09
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
10861	21	tt0060371	0.080598	0	0	The Endless Summer	Michael Hynson|Robert August|Lord 'Tally Ho' B...	NaN	Bruce Brown	NaN	...	The Endless Summer, by Bruce Brown, is one of ...	95	Documentary	Bruce Brown Films	6/15/66	11	7.4	1966	0.000000e+00	0.000000e+00
10862	20379	tt0060472	0.065543	0	0	Grand Prix	James Garner|Eva Marie Saint|Yves Montand|Tosh...	NaN	John Frankenheimer	Cinerama sweeps YOU into a drama of speed and ...	...	Grand Prix driver Pete Aron is fired by his te...	176	Action|Adventure|Drama	Cherokee Productions|Joel Productions|Douglas ...	12/21/66	20	5.7	1966	0.000000e+00	0.000000e+00
10863	39768	tt0060161	0.065141	0	0	Beregis Avtomobilya	Innokentiy Smoktunovskiy|Oleg Efremov|Georgi Z...	NaN	Eldar Ryazanov	NaN	...	An insurance agent who moonlights as a carthie...	94	Mystery|Comedy	Mosfilm	1/1/66	11	6.5	1966	0.000000e+00	0.000000e+00
10864	21449	tt0061177	0.064317	0	0	What's Up, Tiger Lily?	Tatsuya Mihashi|Akiko Wakabayashi|Mie Hama|Joh...	NaN	Woody Allen	WOODY ALLEN STRIKES BACK!	...	In comic Woody Allen's film debut, he took the...	80	Action|Comedy	Benedict Pictures Corp.	11/2/66	22	5.4	1966	0.000000e+00	0.000000e+00
10865	22293	tt0060666	0.035919	19000	0	Manos: The Hands of Fate	Harold P. Warren|Tom Neyman|John Reynolds|Dian...	NaN	Harold P. Warren	It's Shocking! It's Beyond Your Imagination!	...	A family gets lost on the road and stumbles up...	74	Horror	Norm-Iris	11/15/66	15	1.5	1966	1.276423e+05	0.000000e+00

10866 rows × 21 columns

# get information about data
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10866 entries, 0 to 10865
Data columns (total 21 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   id                    10866 non-null  int64  
 1   imdb_id               10856 non-null  object 
 2   popularity            10866 non-null  float64
 3   budget                10866 non-null  int64  
 4   revenue               10866 non-null  int64  
 5   original_title        10866 non-null  object 
 6   cast                  10790 non-null  object 
 7   homepage              2936 non-null   object 
 8   director              10822 non-null  object 
 9   tagline               8042 non-null   object 
 10  keywords              9373 non-null   object 
 11  overview              10862 non-null  object 
 12  runtime               10866 non-null  int64  
 13  genres                10843 non-null  object 
 14  production_companies  9836 non-null   object 
 15  release_date          10866 non-null  object 
 16  vote_count            10866 non-null  int64  
 17  vote_average          10866 non-null  float64
 18  release_year          10866 non-null  int64  
 19  budget_adj            10866 non-null  float64
 20  revenue_adj           10866 non-null  float64
dtypes: float64(4), int64(6), object(11)
memory usage: 1.7+ MB

df.describe()

	id	popularity	budget	revenue	runtime	vote_count	vote_average	release_year	budget_adj	revenue_adj
count	10866.000000	10866.000000	1.086600e+04	1.086600e+04	10866.000000	10866.000000	10866.000000	10866.000000	1.086600e+04	1.086600e+04
mean	66064.177434	0.646441	1.462570e+07	3.982332e+07	102.070863	217.389748	5.974922	2001.322658	1.755104e+07	5.136436e+07
std	92130.136561	1.000185	3.091321e+07	1.170035e+08	31.381405	575.619058	0.935142	12.812941	3.430616e+07	1.446325e+08
min	5.000000	0.000065	0.000000e+00	0.000000e+00	0.000000	10.000000	1.500000	1960.000000	0.000000e+00	0.000000e+00
25%	10596.250000	0.207583	0.000000e+00	0.000000e+00	90.000000	17.000000	5.400000	1995.000000	0.000000e+00	0.000000e+00
50%	20669.000000	0.383856	0.000000e+00	0.000000e+00	99.000000	38.000000	6.000000	2006.000000	0.000000e+00	0.000000e+00
75%	75610.000000	0.713817	1.500000e+07	2.400000e+07	111.000000	145.750000	6.600000	2011.000000	2.085325e+07	3.369710e+07
max	417859.000000	32.985763	4.250000e+08	2.781506e+09	900.000000	9767.000000	9.200000	2015.000000	4.250000e+08	2.827124e+09

#check null values in data
df.isna().sum()

id                         0
imdb_id                   10
popularity                 0
budget                     0
revenue                    0
original_title             0
cast                      76
homepage                7930
director                  44
tagline                 2824
keywords                1493
overview                   4
runtime                    0
genres                    23
production_companies    1030
release_date               0
vote_count                 0
vote_average               0
release_year               0
budget_adj                 0
revenue_adj                0
dtype: int64

# Check duplicated
df.duplicated().sum()

1

#dropping unuseful columns
df.drop(labels =['id', 'imdb_id', 'budget', 'revenue', 'cast', 'homepage', 'tagline', 'overview', 'release_date', 'vote_count', 'vote_average'],
        axis=1, inplace=True)
df.shape

(10866, 10)

df.head()

	popularity	original_title	director	keywords	runtime	genres	production_companies	release_year	budget_adj	revenue_adj
0	32.985763	Jurassic World	Colin Trevorrow	monster|dna|tyrannosaurus rex|velociraptor|island	124	Action|Adventure|Science Fiction|Thriller	Universal Studios|Amblin Entertainment|Legenda...	2015	1.379999e+08	1.392446e+09
1	28.419936	Mad Max: Fury Road	George Miller	future|chase|post-apocalyptic|dystopia|australia	120	Action|Adventure|Science Fiction|Thriller	Village Roadshow Pictures|Kennedy Miller Produ...	2015	1.379999e+08	3.481613e+08
2	13.112507	Insurgent	Robert Schwentke	based on novel|revolution|dystopia|sequel|dyst...	119	Adventure|Science Fiction|Thriller	Summit Entertainment|Mandeville Films|Red Wago...	2015	1.012000e+08	2.716190e+08
3	11.173104	Star Wars: The Force Awakens	J.J. Abrams	android|spaceship|jedi|space opera|3d	136	Action|Adventure|Science Fiction|Fantasy	Lucasfilm|Truenorth Productions|Bad Robot	2015	1.839999e+08	1.902723e+09
4	9.335014	Furious 7	James Wan	car race|speed|revenge|suspense|car	137	Action|Crime|Thriller	Universal Pictures|Original Film|Media Rights ...	2015	1.747999e+08	1.385749e+09

#dropping NaN rows
df.dropna(inplace=True)
df.isna().sum()

popularity              0
original_title          0
director                0
keywords                0
runtime                 0
genres                  0
production_companies    0
release_year            0
budget_adj              0
revenue_adj             0
dtype: int64

#dropping duplicated row
df.drop_duplicates(inplace=True)
df.duplicated().sum()

0

#dropping rows with zeros in badget or revenue
df['budget_adj'] = df['budget_adj'].replace(0, np.NaN)
df['revenue_adj'] = df['revenue_adj'].replace(0, np.NaN)
df.dropna(inplace=True)
df.isna().sum()

popularity              0
original_title          0
director                0
keywords                0
runtime                 0
genres                  0
production_companies    0
release_year            0
budget_adj              0
revenue_adj             0
dtype: int64

Exploratory Data Analysis

Question 1: How are the budget of making a movie changed over time?

#plotting barplot for Average Budget over time
x=df.groupby('release_year').budget_adj.mean().index
y=df.groupby('release_year').budget_adj.mean().values

fig = px.line(x=x, y=y, labels={
                     'x': "Release Year", 'y':'Budget (Adj)'},
                     title="Average Spending over Time")
#show the plot
fig.show()

Question 2 : Which movies have the most and least profit?

#making new column for profit
df['profit'] = df['revenue_adj'] - df['budget_adj']
#finding movies with highest and lowest profit 
lowest =  pd.DataFrame(df.loc[df['profit'].idxmin()])
highest = pd.DataFrame(df.loc[df['profit'].idxmax()])
high_low = pd.concat([highest, lowest],axis=1)
high_low

	1329	2244
popularity	12.037933	0.25054
original_title	Star Wars	The Warrior's Way
director	George Lucas	Sngmoo Lee
keywords	android|galaxy|hermit|death star|lightsaber	assassin|small town|revenge|deception|super speed
runtime	121	100
genres	Adventure|Action|Science Fiction	Adventure|Fantasy|Action|Western|Thriller
production_companies	Lucasfilm|Twentieth Century Fox Film Corporation	Boram Entertainment Inc.
release_year	1977	2010
budget_adj	39575591.358274	425000000.0
revenue_adj	2789712242.27745	11087569.0
profit	2750136650.919176	-413912431.0

plotting BarChart for highest profitable movies

df_pf = pd.DataFrame(df['profit'].sort_values(ascending =False))
df_pf['original_title'] = df['original_title']
fig = px.bar(x=df_pf['original_title'][:10], y=df_pf['profit'][:10],
            labels={'x': " ", 'y':'Profit'},
            title="Top 10 Movies with highest profit")
#show the plot
fig.show()

from the figures above 'Star Wars' movie Directed by George Lucas earn the highest profit in all, making over 2.7B in profit in this dataset.

The most in loss movie is The Warrior's Way. Going in loss by more than 400M was directed by Singmoo Lee

Question 3 : Which genre are most popular from year to year?

#splitting genres
df_gen=df[['genres','release_year','popularity']].copy()
df_gen['genres'] = df_gen['genres'].str.split('|')
df_gen

	genres	release_year	popularity
0	[Action, Adventure, Science Fiction, Thriller]	2015	32.985763
1	[Action, Adventure, Science Fiction, Thriller]	2015	28.419936
2	[Adventure, Science Fiction, Thriller]	2015	13.112507
3	[Action, Adventure, Science Fiction, Fantasy]	2015	11.173104
4	[Action, Crime, Thriller]	2015	9.335014
...	...	...	...
10822	[Drama]	1966	0.670274
10828	[Mystery, Thriller]	1966	0.402730
10829	[Action, Western]	1966	0.395668
10835	[Action, Adventure, Drama, War, Romance]	1966	0.299911
10848	[Adventure, Science Fiction]	1966	0.207257

3679 rows × 3 columns

gen = df_gen.apply(lambda x: pd.Series(x['genres']),axis=1).stack().reset_index(level=1, drop=True)
gen = df_gen.apply(lambda x: pd.Series(x['genres']),axis=1).stack().reset_index(level=1, drop=True)
gen.name = 'genres'
df_gen.drop('genres',axis=1,inplace=True)
df_gen=df_gen.join(gen)
df_gen

	release_year	popularity	genres
0	2015	32.985763	Action
0	2015	32.985763	Adventure
0	2015	32.985763	Science Fiction
0	2015	32.985763	Thriller
1	2015	28.419936	Action
...	...	...	...
10835	1966	0.299911	Drama
10835	1966	0.299911	War
10835	1966	0.299911	Romance
10848	1966	0.207257	Adventure
10848	1966	0.207257	Science Fiction

9860 rows × 3 columns

plotting barplot for most frequent genres

x=df_gen['genres'].value_counts().index
y=df_gen['genres'].value_counts().values
fig = px.bar(x=x, y=y, labels={
                     'x': "", 'y':'Count'},
                     title="Genres Occurances")
fig.show()

Plotting pieplot to see percentage of each genre

y = df_gen['genres'].value_counts().values[13:]
sy = sum(y)

gen = df_gen['genres'].value_counts()
gen = gen.drop(labels = ['Music','History','War','Western','Documentary','Foreign','TV Movie'])

gen['Others']=sy

gen

Drama              1667
Comedy             1280
Thriller           1160
Action             1043
Adventure           725
Romance             628
Crime               628
Science Fiction     510
Horror              445
Family              403
Fantasy             385
Mystery             337
Animation           195
Others              454
Name: genres, dtype: int64

x=gen.index
y=gen.values
fig = px.pie(values=y, names=x, 
                     title="Genres Percentages ")
fig.show()

from the figures above Drama has the highest number of released movies followed by Comedy

splitting genres into Decades

df_gen

	release_year	popularity	genres
0	2015	32.985763	Action
0	2015	32.985763	Adventure
0	2015	32.985763	Science Fiction
0	2015	32.985763	Thriller
1	2015	28.419936	Action
...	...	...	...
10835	1966	0.299911	Drama
10835	1966	0.299911	War
10835	1966	0.299911	Romance
10848	1966	0.207257	Adventure
10848	1966	0.207257	Science Fiction

9860 rows × 3 columns

plotting most popular genres for each year

def f(year):
    b = df_gen[df_gen["release_year"]==year].groupby('genres').popularity.sum().sort_values(ascending=False)
    fig = px.bar(x=b.index, y=b.values,       
              labels={'y':'Popularity', 'x':'Genres'},
              title= f'Most Popular genres in {year}')
    fig.show()
interact(f, year=list(set(df_gen["release_year"])));

most frequently entered genres in the top 5 (in terms of popularity) in each decade are:

Drama

Action

Comedy

Thriller

Adventure

Most Popular Keywords?

 pip install wordcloud

Requirement already satisfied: wordcloud in e:\anaconda3\lib\site-packages (1.8.1)
Requirement already satisfied: pillow in e:\anaconda3\lib\site-packages (from wordcloud) (8.2.0)
Requirement already satisfied: numpy>=1.6.1 in e:\anaconda3\lib\site-packages (from wordcloud) (1.20.1)
Requirement already satisfied: matplotlib in e:\anaconda3\lib\site-packages (from wordcloud) (3.3.4)
Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.3 in e:\anaconda3\lib\site-packages (from matplotlib->wordcloud) (2.4.7)
Requirement already satisfied: python-dateutil>=2.1 in e:\anaconda3\lib\site-packages (from matplotlib->wordcloud) (2.8.1)
Requirement already satisfied: kiwisolver>=1.0.1 in e:\anaconda3\lib\site-packages (from matplotlib->wordcloud) (1.3.1)
Requirement already satisfied: cycler>=0.10 in e:\anaconda3\lib\site-packages (from matplotlib->wordcloud) (0.10.0)
Requirement already satisfied: six in e:\anaconda3\lib\site-packages (from cycler>=0.10->matplotlib->wordcloud) (1.15.0)
Note: you may need to restart the kernel to use updated packages.

from wordcloud import WordCloud, STOPWORDS
text = df.keywords.str.cat(sep='|')
wordcloud = WordCloud(width=1280, height=720,background_color="black").generate(text)
fig = px.imshow(wordcloud)
fig.show()

#splitting production companies
df_prod = df[['production_companies','profit']].copy()
df_prod['production_companies'] = df_prod['production_companies'].str.split('|')
prod = df_prod.apply(lambda x: pd.Series(x['production_companies']),axis=1).stack().reset_index(level=1, drop=True)
prod.name = 'production_companies'
df_prod.drop('production_companies',axis=1,inplace=True)
df_prod=df_prod.join(prod)
df_prod

	profit	production_companies
0	1.254446e+09	Universal Studios
0	1.254446e+09	Amblin Entertainment
0	1.254446e+09	Legendary Pictures
0	1.254446e+09	Fuji Television Network
0	1.254446e+09	Dentsu
...	...	...
10829	9.049166e+06	Laurel Productions
10835	5.374412e+07	Twentieth Century Fox Film Corporation
10835	5.374412e+07	Solar Productions
10835	5.374412e+07	Robert Wise Productions
10848	4.625353e+07	Twentieth Century Fox Film Corporation

10229 rows × 2 columns

plotting barplot for highest earning production companies

# plotting barplot for highest earning production companies
top_prod = df_prod.groupby('production_companies').profit.sum().sort_values(ascending=True)[-10:]
x=top_prod.values
y=top_prod.index
fig = px.bar(x=x, y=y,orientation='h',labels={'x':"Profit", 'y':''},title="10 Highest Earning Film Production Companies")
fig.show()

Which director has the most popular movies?

top_dir = df.groupby('director').popularity.sum().sort_values(ascending=True)[-10:]
y=top_dir.index
x=top_dir.values
fig = px.bar(x=x, y=y,orientation='h',labels={'x':"Popularity", 'y':''},title="Directors With Most Popular Movies")
fig.show()

Box plot to show statistical representation of budget

x = df['budget_adj']
fig = px.box(df, x)
fig.show()

Box plot to show statistical representation of Revenue

x = df['revenue_adj']
fig = px.box(df, x)
fig.show()

Interactive Scatter Plot between Revenue_adj and Budget_adj

x=df['revenue_adj']
y=df['budget_adj']
fig = px.scatter(x=x, y=y, labels={
                     'x': "Revenue _adj", 'y':'Budget_adj'},
                     title="Revenue  Vs Budget")
fig.show()

import plotly
import plotly.graph_objs as go 
from datetime import datetime

# create figure
fig = go.Figure()

plot = go.Figure(data=[px.scatter(x=df['revenue_adj'],y=df['budget_adj']),
                       px.line( name='Bar Plot',x=df['revenue_adj'],y=df['budget_adj'])])
# Add dropdown
plot.update_layout(
    updatemenus=[
        dict(
            type="buttons",
            direction="left",
            buttons=list([
                dict(label="Sactter Plot",
                     method="update",
                     args=[{"visible": [True, False]},
                           {"title": "Sactter Plot",
                            }]),
                dict(label="Bar Plot",
                     method="update",
                     args=[{"visible": [False, True]},
                           {"title": "Bar Plot",
                            }]),
            ]),
        )
    ])
  
plot.show()

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-35-347eedb081c9> in <module>
      1 plot = go.Figure(data=[px.scatter(x=df['revenue_adj'],y=df['budget_adj']),
----> 2                        px.line( name='Bar Plot',x=df['revenue_adj'],y=df['budget_adj'])])
      3 # Add dropdown
      4 plot.update_layout(
      5     updatemenus=[

TypeError: line() got an unexpected keyword argument 'name'

# Update plot sizing
x=df['revenue_adj']
y=df['budget_adj']
figo.add_trace(go.)
figo.update_layout(
    width=800,
    height=900,
    autosize=False,
    margin=dict(t=0, b=0, l=0, r=0),
    template="plotly_white",
)
figo.update_layout(
    updatemenus=[
        dict(
            type = "buttons",
            direction = "left",
            buttons=list([
                dict(
                    args=["type", "line"],
                    label="Line Chart",
                    method="restyle"
                ),
                dict(
                    args=["type", "scatter"],
                    label="Scatter Plot",
                    method="restyle"
                )
            ]),
            pad={"r": 10, "t": 10},
            showactive=True,
            x=0.11,
            xanchor="left",
            y=1.1,
            yanchor="top"
        ),
    ]
)

figo.show()

Interactive Scatter Plot between Revenue_adj and Popularity

x=df['revenue_adj']
y=df['popularity']
fig = px.scatter(x=x, y=y, labels={
                     'x': "Revenue _adj", 'y':'Popularity'},
                     title="Revenue  Vs Popularity")
fig.show()

#correlation heatmap to find properties that associated with high revenues movies 
corr = df[['revenue_adj','budget_adj','popularity','runtime']].corr()

fig = px.imshow(corr,color_continuous_scale=px.colors.sequential.Blues,
                     title = 'Revenue Vs (Budget,Runtime,Popularity)')
fig.show()

Budget vs Revenue:

• we can see that the revenues increase slightly at higher levels (moderate Correlation),
• So There is a possibility that movies with higher investments result in better revenues. Correlation = 0.57

Popularity vs Revenue:

• we can see that the revenue seems to be slightly increasing with popularity (moderate Correlation),
• We can say that movies with higher Popularity get higher revenue. Correlation = 0.54

Runtime vs Revenue:

• The correlation between revenue and runtime is 0.28 (weak corelation).
• So runtime is not highly related to the revenue.

Question : What are Average runtime, budget and revenue of all the movies?

#plotting a histogram of runtime of movies
fig = px.histogram(x = df['runtime'], 
                       labels={'x':'Runtime'},
                      title = 'Distribution of Runtime',
                      nbins=35)
fig.show()

The distribution of the above graph show that Most of the movies are timed between 90 to 120 minutes.¶

#plotting a histogram of Budget of movies
fig = px.histogram(x = df['budget_adj'], 
                       labels={'x':'Budget'},
                      title = 'Distribution of Budget',
                      nbins=35)
fig.show()

The distribution of the above graph show that Most of the movies have a budget between 10 ~ 50 Million

#plotting a histogram of Revenue of movies
fig = px.histogram(x = df['revenue_adj'], 
                       labels={'x':'Revenue'},
                      title = 'Distribution of Revenue',
                      nbins=40)
fig.show()

The distribution of the above graph show that Most of the movies have a revenue between 50~ 150 Million

Conclusions 🥰

We can summarize our findings in those few points:

• Budget of making movies is increasing over time.
• Star Wars is the most profitable movie ever.

Drama has the highest number of released movies followed by Comedy.

• Most popular genres in each decade are:

1. Drama
2. Action
3. Comedy
4. Thriller
5. Adventure

Most Earning Film Production Companies are:

1. Warner Bros
2. Universal Picture
3. Paramount Pictures
4. 20th Century Studios

Directors with the most popular movies:

1. Christopher Nolan
2. Steven Spielberg
3. Peter Jackson
4. Quentin Tarantino

Movies with higher Budgets and Popularity have shown an increase in the revenues.

• Limitation: ##### there are many data that was removed such as rows contained 0 and null values.